alirezarezvani/eval
engineering/agenthub/skills/eval/SKILL.md
Evaluate and rank agent results by metric or LLM judge for an AgentHub session. Use when the user runs /hub:eval or asks to score, compare, or pick a winner among completed AgentHub agents.
$ install --global
skillsauthnpx skillsauth add alirezarezvani/claude-skills evalInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 13, 2026, 4:22 AM117.1s1 file scanned
SKILL.md
- name:
- eval
- description:
- Evaluate and rank agent results by metric or LLM judge for an AgentHub session. Use when the user runs /hub:eval or asks to score, compare, or pick a winner among completed AgentHub agents.
- command:
- /hub:eval
/hub:eval — Evaluate Agent Results
Rank all agent results for a session. Supports metric-based evaluation (run a command), LLM judge (compare diffs), or hybrid.
Usage
/hub:eval # Eval latest session using configured criteria
/hub:eval 20260317-143022 # Eval specific session
/hub:eval --judge # Force LLM judge mode (ignore metric config)
What It Does
Metric Mode (eval command configured)
Run the evaluation command in each agent's worktree:
python {skill_path}/scripts/result_ranker.py \
--session {session-id} \
--eval-cmd "{eval_cmd}" \
--metric {metric} --direction {direction}
Output:
RANK AGENT METRIC DELTA FILES
1 agent-2 142ms -38ms 2
2 agent-1 165ms -15ms 3
3 agent-3 190ms +10ms 1
Winner: agent-2 (142ms)
LLM Judge Mode (no eval command, or --judge flag)
For each agent:
- Get the diff:
git diff {base_branch}...{agent_branch} - Read the agent's result post from
.agenthub/board/results/agent-{i}-result.md - Compare all diffs and rank by:
- Correctness — Does it solve the task?
- Simplicity — Fewer lines changed is better (when equal correctness)
- Quality — Clean execution, good structure, no regressions
Present rankings with justification.
Example LLM judge output for a content task:
RANK AGENT VERDICT WORD COUNT
1 agent-1 Strong narrative, clear CTA 1480
2 agent-3 Good data points, weak intro 1520
3 agent-2 Generic tone, no differentiation 1350
Winner: agent-1 (strongest narrative arc and call-to-action)
Hybrid Mode
- Run metric evaluation first
- If top agents are within 10% of each other, use LLM judge to break ties
- Present both metric and qualitative rankings
After Eval
- Update session state:
python {skill_path}/scripts/session_manager.py --update {session-id} --state evaluating
- Tell the user:
- Ranked results with winner highlighted
- Next step:
/hub:mergeto merge the winner - Or
/hub:merge {session-id} --agent {winner}to be explicit
Related Skills
alirezarezvani/collab-proof
data-ai
VerifiedTrustedCommunity
Use when you want to understand what Claude contributed vs what you drove in a session. Triggers on: /collab-proof, session retrospective, ai contribution analysis, collaboration evidence, what did claude do.
17,936SKILL.mdUpdated Jun 13, 2026
alirezarezvani/claude-coach
data-ai
VerifiedTrustedCommunity
Personal coach that teaches users to become Claude power users. Use this skill the FIRST time a user asks to "learn Claude", "be a power user", "coach me", "teach me Claude tricks", "what can Claude do", "make me better at prompting", or any variation. After activation, also use it on EVERY subsequent turn to detect missed optimization opportunities (vague prompts, ignored capabilities, manual work Claude could automate) and surface a single power-user tip. Trigger generously — most users do not know what they do not know, so err on the side of coaching.
17,936SKILL.mdUpdated May 23, 2026
alirezarezvani/pricing-strategist
development
VerifiedTrustedCommunity
Use when designing or revisiting product pricing — selecting a pricing model (subscription seat-based, usage-based, value-based, freemium, or hybrid), running Van Westendorp Price Sensitivity Meter analysis on WTP survey data, or designing Good/Better/Best packaging tiers. Recommends a model and a price range with trade-offs, never a single number. For Commercial leads, Product Marketing, and CMOs at the pricing-design moment — not deal-by-deal discounting, not brand positioning.
17,936SKILL.mdUpdated May 20, 2026
alirezarezvani/partnerships-architect
testing
VerifiedTrustedCommunity
Use when a startup is approached by a prospective partner and someone has to decide should we sign this partner, at what partner tier (referral / reseller / OEM / SI-consulting / strategic alliance), with what joint GTM commitment, and at what revshare. Classifies partner tier from independent-demand evidence vs. preferential-terms hunting, designs a 90-day joint GTM plan, models revshare against direct-sale margin, and surfaces kill criteria for unwinding under-performing partnerships. For Head of Partnerships, Head of BD, and Founder-CEOs doing reseller agreement, OEM deal, or strategic alliance review — not technical sale enablement, not channel cost economics, not M&A.
17,936SKILL.mdUpdated May 20, 2026